Wan Mohd Bukhari Wan Daud

Features Extraction of Electromyography Signals in Time Domain on Biceps Brachii Muscle

Electromyography (EMG) is widely used in various fields to investigate the muscular activities. Since EMG signals contain a wealth of information about muscle functions, there are many approaches in analyzing the EMG signals. It is important to know the features that can be extracting from the EMG signal. The ideal feature is important for the achievement in EMG analysis. Hence, the objective of this paper is to evaluate the features extraction of time domain from the EMG signal. The experiment was setup according to surface electromyography for noninvasive assessment of muscle (SENIAM). The recorded data was analyzed in time domain to get the features. Based on the analysis, three features have been considered based on statistical features. The features was then been evaluate by getting the percentage error of each feature. The less percentage error determines the ideal feature. The results shows that the extracted features of the EMG signals in time domain can be implement in signal classification. These findings could be integrated to design a signal classification based on the features extraction.

Modeling of EEG Signal Sound Frequency Characteristic Using Time Frequency Analysis

This paper presents the study of sound frequency characteristic based on Electroencephalography (EEG) signals. The study includes feature extraction of the EEG signals with respect to different sound frequencies, covering low frequency (40 Hz), mid-range frequency (5000 Hz), and high frequency (15000 Hz). Human brain activities are expected to be different when exposed to different sound frequencies, and can be shown through EEG signals. In this paper, EEG signal characterization is done using Fast Fourier Transform (FFT), moving average filters, and simple artefact filtering with reference EEG data per individual. Based on the characteristics of the EEG signal, the sound frequency can be categorized and identified using the proposed method.